International audience

In the recent research of autonomous vehicle (AV) control methods, machine learning techniques are gaining more and more popularity due to their possible performance advantages over classical model based methods. As lane keeping or trajectory tracking through steering intervention is one of the key feature of the autonomous vehicle, several methods had been proposed and utilized both with model and machine learning based controllers. Present paper focuses on the integration of a robust Linear Parameter Varying (LPV) and a Reinforcement Learning (RL) controller in a supervisor structure, with the aim to guarantee stability against disturbances not considered during the training process of the RL agent. Hence, with the supervision of the proposed LPV controller, noisy or faulty GPS signals can be handled safely, without compromising the trajectory tracking performance of the RL agent during normal operation of the autonomous vehicle. For the demonstration of the proposed LPV supervised RL control method, highway simulations have been carried out and compared in CarSim simulation environment.

This paper presents the design and implementation of an intelligent switched control for lateral control of autonomous vehicles. The switched control is designed based on Linear Parameter-Varying (LPV) and Youla-Kucera (YK) parameterization. The proposed intelligent system aims to optimize the control switching performance using a Reinforcement Learning (RL) model. The presented approach studies the critical problem of initial or sudden large lateral errors in lane-tracking or lane-changing. It ensures stable and smooth switching performance to provide a smooth vehicle response regardless of the lateral error. The proposed RL-based switching strategy is validated using a RENAULT simulator on MATLAB, and compared to another modeled switching strategy with encouraging results.

This paper proposed a road adaptive semi-active suspension control method, where a trade-off between driving comfort and vehicle stability/road-holding is accomplishable in order to achieve desirable performance results at different road irregularities and velocities by modifying the scheduling variable that is designed by Fuzzy Logic Control. The proposed semi-active controller is founded on the Linear Parameter-Varying framework. Hungarian highway route data has been implemented into the TruckSim simulation environment based on real geographical data having road irregularities in order to compare the proposed adaptive method with a non-adaptive scenario. Simulation results show that all performances have been improved with the proposed method in different road irregularities and velocities.

This paper presents the design and experimental validation of grid-based and Linear Fractional Transformation (LFT) approaches for the lateral control of autonomous vehicles. These new methodological approaches are compared together with the classical polytopic approach from the theoretical design to the real implementation on a real automated Renault ZOE vehicle. A solution is proposed to deal with both lane change and lane tracking problems, using a single LPV controller, by adapting the look-ahead distance. Each LPV controller is designed based on LPV/$\mathcal {H}_\infty $concept. Performance comparison includes computational costs, vehicle performance (i.e. lateral tracking error or control effort optimization) and on-board integration complexity. Simulation and experimental results on a private test track are included to support main findings.

Based on a Global Chassis Control system with three-layers architecture (decision, control, and physical layers) a Fuzzy Logic (FL) approach is exploited. The FL based decision layer identifies the current driving condition of the vehicle and decides the control strategy to take care of this driving condition. A confusion matrix validates the classification results. The control strategy is implemented through the subsystems (suspension, steering, and braking) at the FL based control layer. The strategy was evaluated under two different tests: slalom and double line change by comparing the performance with an UnControlled system. Early results show the proposed strategy has less roll, yaw movement and side slip angle than an UnControlled system during a double line change maneuver; also, for the slalom test the proposal improves the dynamic vehicle performance allowing the driver to maintain the vehicle under control.

In this paper, a new predictive approach is proposed for the impedance control of bilateral drive-by-wire teleoperation systems. The proposed control structure includes two mirror predictors/observers in both the master and slave sides. These predictors/observers are used to simultaneously estimate the master and slave internal dynamics, and thereby to avoid the use of the delayed transmitted information. As a consequence, the influence of the delay on the whole system can be minimized and the performance can be improved. Under a set of suited hypotheses, the proposed control structure is shown to be uniformly ultimate stable, even in the presence of time-varying delays. Simulation results are presented to show the effectiveness of the proposed approach. The behavior of the control structure is also experimentally demonstrated while performing remote steering of a small autonomous vehicle

Control systems running on a computer are subject to timing disturbances coming from implementation constraints. Fortunately closed-loop systems behave robustly w.r.t. modelling errors and disturbances, and the controller design can be performed to explicitly enhance robustness against specific uncertainties. On one hand robustness in process controllers can be used to comply with weakly modelled timing uncertainties. On the other hand the principle of robust closed-loop control can also be applied to the real-time scheduler to provide online adaption of some scheduling parameters, with the objective of controlling the computing resource allocation. The control performance specification may be set according to both control and implementation constraints. The approach is illustrated through several examples using simulation and an experimental feedback scheduler is briefly described.

This work is devoted to integrated control-scheduling in the case of real-time control of systems with communications delays, i.e. network induced delay and input output latency. Feedback control of computing resources is tackled to deal with CPU resource variations and unpredictable workload. Thus, two new control schemes are provided for feedback scheduling of single and multi control task systems. Moreover, the system control design takes into account the unknown delays due to the temporal uncertainties that are unavoidable in real-time control. A new method of state feedback control design for discrete time-delay systems is presented in a LMI formulation. Two illustrative examples show the interest of the proposed approach.